The dynamics of lung cancer is the major cause of cancer-related deaths worldwide, with poor survival due to the poor diagnostic system at the advanced cancer stage. In the past, researchers developed computer-aided diagnosis (CAD) systems, which radiologists greatly used for identifying abnormalities and applying a few feature-extracting methods.
The physiology and behavior of various physiological systems can be best investigated using nonlinear dynamical measures for capturing the intrinsic dynamics, which are influenced due to multiple pathologies by the degradation of structural and functional components, as cancer images contain confidential information, which can be best analyzed using these dynamic measures. In this paper, we proposed multiscale sample entropy (MSE) with a mean and KD-tree algorithmic approach, multiscale permutation entropy (MPE), multiscale fuzzy entropy (MFE), and refined composite multiscale fuzzy entropy (RCMFE) with mean, variance, and standard deviation. The statistically significant results were computed to distinguish non-small-cell lung cancer (NSCLC) from SCLC by extracting morphological, texture, and elliptic Fourier descriptors (EFDs).
The highest significant results obtained based on texture features using MFE with standard deviation give the P-value of 1.95E-50, morphological features using RCMFE with mean provide the P-value of 3.01E-14, and EFDs features using MFE with variance give the P-value of 1.04E-13. The results reveal that the improved complexity measures based on refined fuzzy entropy outperformed in analyzing the dynamics of lung cancer and will provide new insight into extracting meaningful hidden information present in the Lung cancer images, which will be very helpful to further distinguish NSCLC and SCLC for early diagnosis and prognosis.